Understanding pedestrian behaviors from stationary crowd groups

Pedestrian behavior modeling and analysis is important for crowd scene understanding and has various applica-tions in video surveillance. Stationary crowd groups are a key factor influencing pedestrian walking patterns but was largely ignored in literature. In this paper, a novel model is proposed for pedestrian behavior modeling by including stationary crowd groups as a key component. Through inference on the interactions between stationary crowd groups and pedestrians, our model can be used to investigate pedestrian behaviors. The effectiveness of the proposed model is demonstrated through multiple applica-tions, including walking path prediction, destination pre-diction, personality classification, and abnormal event de-tection. To evaluate our model, a large pedestrian walking route dataset 1 is built. The walking routes of 12, 684 pedes-trians from a one-hour crowd surveillance video are manu-ally annotated. It will be released to the public and benefit future research on pedestrian behavior analysis and crowd scene understanding. 1